Cognition's new flash model is post-trained on top of Inkling-small!
Cognition introduces SWE-2 Flash, a fast open-weight coding model
AICognition introduces SWE-2 Flash, a fast and efficient coding model that it says outperforms all American open-weight models on leading evals, including ones three times larger. Cognition says it is building a program to securely share the weights with partners and researchers, balancing transparency against cyber risks.
Soumith ChintalaVerified on X
@soumithchintala
Introducing SWE-2 Flash, our new fast & efficient coding model. On leading evals, it outperforms all American open-weight models, even ones 3x larger. To balance transparency and cyber risks, we are building a program to securely share the weights with partners & researchers.
Source details
Soumith Chintala · x.comPublished · added here
Original title: Cognition's new flash model is post-trained on top of Inkling-small!